rails/activerecord/test/cases/sanitize_test.rb
Jonathan Hefner c02d6bfb27 Improve sanitize_sql_like performance
This improves performance and reduces memory allocations for
`sanitize_sql_like` across multiple use cases.

Benchmark script:

```ruby
require "benchmark/memory"
require "benchmark/ips"

def old_sanitize_sql_like(string, escape_character = "\\")
  pattern = Regexp.union(escape_character, "%", "_")
  string.gsub(pattern) { |x| [escape_character, x].join }
end

def new_sanitize_sql_like(string, escape_character = "\\")
  if string.include?(escape_character) && escape_character != "%" && escape_character != "_"
    string = string.gsub(escape_character, '\0\0')
  end

  string.gsub(/(?=[%_])/, escape_character)
end

[
  "no-special-characters",
  "one_wildcard",
  "one\\escape",
  "two_wildcards%and\\two\\escapes",
].each do |string|
  puts "\n= #{string.inspect} ".ljust(72, "=")

  Benchmark.memory do |x|
    # Warmup:
    old_sanitize_sql_like(string)
    new_sanitize_sql_like(string)

    x.report("old") { old_sanitize_sql_like(string) }
    x.report("new") { new_sanitize_sql_like(string) }
  end

  puts

  Benchmark.ips do |x|
    x.report("old") { old_sanitize_sql_like(string) }
    x.report("new") { new_sanitize_sql_like(string) }
    x.compare!
  end
end
```

Benchmark results:

```
= "no-special-characters" =============================================
Calculating -------------------------------------
                 old   875.000  memsize (     0.000  retained)
                        10.000  objects (     0.000  retained)
                         5.000  strings (     0.000  retained)
                 new    40.000  memsize (     0.000  retained)
                         1.000  objects (     0.000  retained)
                         1.000  strings (     0.000  retained)

Warming up --------------------------------------
                 old     9.483k i/100ms
                 new   119.791k i/100ms
Calculating -------------------------------------
                 old     95.694k (± 0.3%) i/s -    483.633k in   5.053985s
                 new      1.228M (± 0.5%) i/s -      6.229M in   5.072317s

Comparison:
                 new:  1228094.1 i/s
                 old:    95694.3 i/s - 12.83x  (± 0.00) slower

= "one_wildcard" ======================================================
Calculating -------------------------------------
                 old     1.395k memsize (     0.000  retained)
                        15.000  objects (     0.000  retained)
                         6.000  strings (     0.000  retained)
                 new   440.000  memsize (     0.000  retained)
                         3.000  objects (     0.000  retained)
                         1.000  strings (     0.000  retained)

Warming up --------------------------------------
                 old     6.527k i/100ms
                 new    30.205k i/100ms
Calculating -------------------------------------
                 old     65.255k (± 0.6%) i/s -    326.350k in   5.001318s
                 new    300.058k (± 0.5%) i/s -      1.510M in   5.033333s

Comparison:
                 new:   300057.6 i/s
                 old:    65255.2 i/s - 4.60x  (± 0.00) slower

= "one\\escape" =======================================================
Calculating -------------------------------------
                 old     1.395k memsize (     0.000  retained)
                        15.000  objects (     0.000  retained)
                         6.000  strings (     0.000  retained)
                 new   560.000  memsize (     0.000  retained)
                         6.000  objects (     0.000  retained)
                         2.000  strings (     0.000  retained)

Warming up --------------------------------------
                 old     6.506k i/100ms
                 new    24.312k i/100ms
Calculating -------------------------------------
                 old     65.467k (± 0.4%) i/s -    331.806k in   5.068392s
                 new    245.704k (± 0.5%) i/s -      1.240M in   5.046485s

Comparison:
                 new:   245703.8 i/s
                 old:    65466.9 i/s - 3.75x  (± 0.00) slower

= "two_wildcards%and\\two\\escapes" ===================================
Calculating -------------------------------------
                 old     1.755k memsize (     0.000  retained)
                        24.000  objects (     0.000  retained)
                         8.000  strings (     0.000  retained)
                 new   832.000  memsize (     0.000  retained)
                         8.000  objects (     0.000  retained)
                         3.000  strings (     0.000  retained)

Warming up --------------------------------------
                 old     5.265k i/100ms
                 new    12.360k i/100ms
Calculating -------------------------------------
                 old     52.698k (± 0.3%) i/s -    268.515k in   5.095425s
                 new    124.006k (± 0.3%) i/s -    630.360k in   5.083351s

Comparison:
                 new:   124006.2 i/s
                 old:    52697.9 i/s - 2.35x  (± 0.00) slower
```
2022-03-25 12:55:10 -05:00

236 lines
9.5 KiB
Ruby

# frozen_string_literal: true
require "cases/helper"
require "models/binary"
require "models/author"
require "models/post"
require "models/customer"
class SanitizeTest < ActiveRecord::TestCase
def setup
end
def test_sanitize_sql_array_handles_string_interpolation
quoted_bambi = ActiveRecord::Base.connection.quote_string("Bambi")
assert_equal "name='#{quoted_bambi}'", Binary.sanitize_sql_array(["name='%s'", "Bambi"])
assert_equal "name='#{quoted_bambi}'", Binary.sanitize_sql_array(["name='%s'", "Bambi".mb_chars])
quoted_bambi_and_thumper = ActiveRecord::Base.connection.quote_string("Bambi\nand\nThumper")
assert_equal "name='#{quoted_bambi_and_thumper}'", Binary.sanitize_sql_array(["name='%s'", "Bambi\nand\nThumper"])
assert_equal "name='#{quoted_bambi_and_thumper}'", Binary.sanitize_sql_array(["name='%s'", "Bambi\nand\nThumper".mb_chars])
end
def test_sanitize_sql_array_handles_bind_variables
quoted_bambi = ActiveRecord::Base.connection.quote("Bambi")
assert_equal "name=#{quoted_bambi}", Binary.sanitize_sql_array(["name=?", "Bambi"])
assert_equal "name=#{quoted_bambi}", Binary.sanitize_sql_array(["name=?", "Bambi".mb_chars])
quoted_bambi_and_thumper = ActiveRecord::Base.connection.quote("Bambi\nand\nThumper")
assert_equal "name=#{quoted_bambi_and_thumper}", Binary.sanitize_sql_array(["name=?", "Bambi\nand\nThumper"])
assert_equal "name=#{quoted_bambi_and_thumper}", Binary.sanitize_sql_array(["name=?", "Bambi\nand\nThumper".mb_chars])
end
def test_sanitize_sql_array_handles_named_bind_variables
quoted_bambi = ActiveRecord::Base.connection.quote("Bambi")
assert_equal "name=#{quoted_bambi}", Binary.sanitize_sql_array(["name=:name", name: "Bambi"])
if current_adapter?(:Mysql2Adapter)
assert_equal "name=#{quoted_bambi} AND id='1'", Binary.sanitize_sql_array(["name=:name AND id=:id", name: "Bambi", id: 1])
else
assert_equal "name=#{quoted_bambi} AND id=1", Binary.sanitize_sql_array(["name=:name AND id=:id", name: "Bambi", id: 1])
end
quoted_bambi_and_thumper = ActiveRecord::Base.connection.quote("Bambi\nand\nThumper")
assert_equal "name=#{quoted_bambi_and_thumper}", Binary.sanitize_sql_array(["name=:name", name: "Bambi\nand\nThumper"])
assert_equal "name=#{quoted_bambi_and_thumper} AND name2=#{quoted_bambi_and_thumper}", Binary.sanitize_sql_array(["name=:name AND name2=:name", name: "Bambi\nand\nThumper"])
end
def test_sanitize_sql_array_handles_relations
david = Author.create!(name: "David")
david_posts = david.posts.select(:id)
sub_query_pattern = /\(\bselect\b.*?\bwhere\b.*?\)/i
select_author_sql = Post.sanitize_sql_array(["id in (?)", david_posts])
assert_match(sub_query_pattern, select_author_sql, "should sanitize `Relation` as subquery for bind variables")
select_author_sql = Post.sanitize_sql_array(["id in (:post_ids)", post_ids: david_posts])
assert_match(sub_query_pattern, select_author_sql, "should sanitize `Relation` as subquery for named bind variables")
end
def test_sanitize_sql_array_handles_empty_statement
select_author_sql = Post.sanitize_sql_array([""])
assert_equal("", select_author_sql)
end
def test_sanitize_sql_like
assert_equal '100\%', Binary.sanitize_sql_like("100%")
assert_equal 'snake\_cased\_string', Binary.sanitize_sql_like("snake_cased_string")
assert_equal 'C:\\\\Programs\\\\MsPaint', Binary.sanitize_sql_like('C:\\Programs\\MsPaint')
assert_equal "normal string 42", Binary.sanitize_sql_like("normal string 42")
end
def test_sanitize_sql_like_with_custom_escape_character
assert_equal "100!%", Binary.sanitize_sql_like("100%", "!")
assert_equal "snake!_cased!_string", Binary.sanitize_sql_like("snake_cased_string", "!")
assert_equal "great!!", Binary.sanitize_sql_like("great!", "!")
assert_equal 'C:\\Programs\\MsPaint', Binary.sanitize_sql_like('C:\\Programs\\MsPaint', "!")
assert_equal "normal string 42", Binary.sanitize_sql_like("normal string 42", "!")
end
def test_sanitize_sql_like_with_wildcard_as_escape_character
assert_equal "1__000_%", Binary.sanitize_sql_like("1_000%", "_")
assert_equal "1%_000%%", Binary.sanitize_sql_like("1_000%", "%")
end
def test_sanitize_sql_like_example_use_case
searchable_post = Class.new(Post) do
def self.search_as_method(term)
where("title LIKE ?", sanitize_sql_like(term, "!"))
end
scope :search_as_scope, -> (term) {
where("title LIKE ?", sanitize_sql_like(term, "!"))
}
end
assert_sql(/LIKE '20!% !_reduction!_!!'/) do
searchable_post.search_as_method("20% _reduction_!").to_a
end
assert_sql(/LIKE '20!% !_reduction!_!!'/) do
searchable_post.search_as_scope("20% _reduction_!").to_a
end
end
def test_disallow_raw_sql_with_unknown_attribute_string
assert_raise(ActiveRecord::UnknownAttributeReference) { Binary.disallow_raw_sql!(["field(id, ?)"]) }
end
def test_disallow_raw_sql_with_unknown_attribute_sql_literal
assert_nothing_raised { Binary.disallow_raw_sql!([Arel.sql("field(id, ?)")]) }
end
def test_bind_arity
assert_nothing_raised { bind "" }
assert_raise(ActiveRecord::PreparedStatementInvalid) { bind "", 1 }
assert_raise(ActiveRecord::PreparedStatementInvalid) { bind "?" }
assert_nothing_raised { bind "?", 1 }
assert_raise(ActiveRecord::PreparedStatementInvalid) { bind "?", 1, 1 }
end
def test_named_bind_variables
if current_adapter?(:Mysql2Adapter)
assert_equal "'1'", bind(":a", a: 1) # ' ruby-mode
assert_equal "'1' '1'", bind(":a :a", a: 1) # ' ruby-mode
else
assert_equal "1", bind(":a", a: 1) # ' ruby-mode
assert_equal "1 1", bind(":a :a", a: 1) # ' ruby-mode
end
assert_nothing_raised { bind("'+00:00'", foo: "bar") }
end
def test_named_bind_arity
assert_nothing_raised { bind "name = :name", name: "37signals" }
assert_nothing_raised { bind "name = :name", name: "37signals", id: 1 }
assert_raise(ActiveRecord::PreparedStatementInvalid) { bind "name = :name", id: 1 }
end
class SimpleEnumerable
include Enumerable
def initialize(ary)
@ary = ary
end
def each(&b)
@ary.each(&b)
end
end
def test_bind_enumerable
quoted_abc = %(#{ActiveRecord::Base.connection.quote('a')},#{ActiveRecord::Base.connection.quote('b')},#{ActiveRecord::Base.connection.quote('c')})
if current_adapter?(:Mysql2Adapter)
assert_equal "'1','2','3'", bind("?", [1, 2, 3])
else
assert_equal "1,2,3", bind("?", [1, 2, 3])
end
assert_equal quoted_abc, bind("?", %w(a b c))
if current_adapter?(:Mysql2Adapter)
assert_equal "'1','2','3'", bind(":a", a: [1, 2, 3])
else
assert_equal "1,2,3", bind(":a", a: [1, 2, 3])
end
assert_equal quoted_abc, bind(":a", a: %w(a b c)) # '
if current_adapter?(:Mysql2Adapter)
assert_equal "'1','2','3'", bind("?", SimpleEnumerable.new([1, 2, 3]))
else
assert_equal "1,2,3", bind("?", SimpleEnumerable.new([1, 2, 3]))
end
assert_equal quoted_abc, bind("?", SimpleEnumerable.new(%w(a b c)))
if current_adapter?(:Mysql2Adapter)
assert_equal "'1','2','3'", bind(":a", a: SimpleEnumerable.new([1, 2, 3]))
else
assert_equal "1,2,3", bind(":a", a: SimpleEnumerable.new([1, 2, 3]))
end
assert_equal quoted_abc, bind(":a", a: SimpleEnumerable.new(%w(a b c))) # '
end
def test_bind_empty_enumerable
quoted_nil = ActiveRecord::Base.connection.quote(nil)
assert_equal quoted_nil, bind("?", [])
assert_equal " in (#{quoted_nil})", bind(" in (?)", [])
assert_equal "foo in (#{quoted_nil})", bind("foo in (?)", [])
end
def test_bind_range
quoted_abc = %(#{ActiveRecord::Base.connection.quote('a')},#{ActiveRecord::Base.connection.quote('b')},#{ActiveRecord::Base.connection.quote('c')})
if current_adapter?(:Mysql2Adapter)
assert_equal "'0'", bind("?", 0..0)
assert_equal "'1','2','3'", bind("?", 1..3)
else
assert_equal "0", bind("?", 0..0)
assert_equal "1,2,3", bind("?", 1..3)
end
assert_equal quoted_abc, bind("?", "a"..."d")
end
def test_bind_empty_range
quoted_nil = ActiveRecord::Base.connection.quote(nil)
assert_equal quoted_nil, bind("?", 0...0)
assert_equal quoted_nil, bind("?", "a"..."a")
end
def test_bind_empty_string
quoted_empty = ActiveRecord::Base.connection.quote("")
assert_equal quoted_empty, bind("?", "")
end
def test_bind_chars
quoted_bambi = ActiveRecord::Base.connection.quote("Bambi")
quoted_bambi_and_thumper = ActiveRecord::Base.connection.quote("Bambi\nand\nThumper")
assert_equal "name=#{quoted_bambi}", bind("name=?", "Bambi")
assert_equal "name=#{quoted_bambi_and_thumper}", bind("name=?", "Bambi\nand\nThumper")
assert_equal "name=#{quoted_bambi}", bind("name=?", "Bambi".mb_chars)
assert_equal "name=#{quoted_bambi_and_thumper}", bind("name=?", "Bambi\nand\nThumper".mb_chars)
end
def test_named_bind_with_postgresql_type_casts
l = Proc.new { bind(":a::integer '2009-01-01'::date", a: "10") }
assert_nothing_raised(&l)
assert_equal "#{ActiveRecord::Base.connection.quote('10')}::integer '2009-01-01'::date", l.call
end
private
def bind(statement, *vars)
if vars.first.is_a?(Hash)
ActiveRecord::Base.send(:replace_named_bind_variables, statement, vars.first)
else
ActiveRecord::Base.send(:replace_bind_variables, statement, vars)
end
end
end